Estimating the proportion of signal variables under arbitrary covariance dependence

DOI10.1214/23-EJS2119arXiv2102.09053OpenAlexW3131901029MaRDI QIDQ6158210FDOQ6158210

Authors:

Publication date: 31 May 2023

Published in: Electronic Journal of Statistics (Search for Journal in Brave)

Abstract: Estimating the proportion of signals hidden in a large amount of noise variables is of interest in many scientific inquires. In this paper, we consider realistic but theoretically challenging settings with arbitrary covariance dependence between variables. We define mean absolute correlation (MAC) to measure the overall dependence level and investigate a family of estimators for their performances in the full range of MAC. We explicit the joint effect of MAC dependence and signal sparsity on the performances of the family of estimators and discover that no single estimator in the family is most powerful under different MAC dependence levels. Informed by the theoretical insight, we propose a new estimator to better adapt to arbitrary covariance dependence. The proposed method compares favorably to several existing methods in extensive finite-sample settings with strong to weak covariance dependence and real dependence structures from genetic association studies.

Full work available at URL: https://arxiv.org/abs/2102.09053

zbMATH Keywords

sparse signalhigh-dimension datalower bound estimatordependence adaptivity

Mathematics Subject Classification ID

Point estimation (62F10) Robustness and adaptive procedures (parametric inference) (62F35)

Cites Work

• Estimating false discovery proportion under arbitrary covariance dependence
• Global testing under sparse alternatives: ANOVA, multiple comparisons and the higher criticism
• Estimating the proportion of false null hypotheses among a large number of independently tested hypotheses
• A stochastic process approach to false discovery control.
• Estimation and confidence sets for sparse normal mixtures
• The effect of correlation in false discovery rate estimation
• Proportion of Non-Zero Normal Means: Universal Oracle Equivalences and Uniformly Consistent Estimators
• A Direct Approach to False Discovery Rates
• Two-Sample Covariance Matrix Testing and Support Recovery in High-Dimensional and Sparse Settings
• Estimating the Null and the Proportion of Nonnull Effects in Large-Scale Multiple Comparisons
• Size, power and false discovery rates
• The positive false discovery rate: A Bayesian interpretation and the \(q\)-value
• Optimal screening and discovery of sparse signals with applications to multistage high throughput studies
• A normal comparison inequality and its applications
• Controlling the Familywise Error Rate with Plug-in Estimator for the Proportion of True Null Hypotheses
• Penalized Composite Quasi-Likelihood for Ultrahigh Dimensional Variable Selection
• On empirical distribution function of high-dimensional Gaussian vector components with an application to multiple testing
• Simultaneous high-probability bounds on the false discovery proportion in structured, regression and online settings
• Post hoc confidence bounds on false positives using reference families
• Permutation-based simultaneous confidence bounds for the false discovery proportion
• Efficient signal inclusion with genomic applications
• Uniformly consistently estimating the proportion of false null hypotheses via Lebesgue-Stieltjes integral equations
• Variable selection via adaptive false negative control in linear regression

Cited In (1)

• Статистическая оценка множества существенных аргументов двоичной вектор-функции с искаженными значениями

This page was built for publication: Estimating the proportion of signal variables under arbitrary covariance dependence

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6158210)